
Stable Diffusion Web UI (AUTOMATIC1111)
β Text source-checked Oct 24, 2026A web interface for Stable Diffusion implemented using the Gradio library.
Source-checked against the vendor's site Β· rebuilt from the vendor's own pagesProfile updated Link checked How we rate
In short
Stable Diffusion Web UI is a free Gradio-based interface for generating images with Stable Diffusion models. It supports advanced features like prompt editing, face fixing, and training LoRAs on NVidia GPUs.
Stable Diffusion Web UI is a web interface for Stable Diffusion implemented using the Gradio library.
Users can utilize X/Y/Z plots to draw 3-dimensional plots of images with different parameters. The tool allows users to specify parts of text that the model should pay more attention to via attention weighting. Prompt editing enables changing the prompt mid-generation, such as switching from one subject to another midway through the process. A negative prompt field allows users to list elements they do not want to see in the generated image.
The Extras tab includes GFPGAN, a neural network that fixes faces. RealESRGAN is available as a neural network upscaler in the Extras tab. A Checkpoint Merger tab allows users to merge up to 3 checkpoints into one.
The Training tab provides options for hypernetworks and embeddings. LoRAs are supported as a feature similar to Hypernetworks.
The software supports 4GB video cards, with reports of it working on 2GB cards. Installation instructions are provided for NVidia GPUs, which are recommended.
According to Stable Diffusion Web UI (AUTOMATIC1111): Stable Diffusion Web UI is a web interface for Stable Diffusion implemented using the Gradio library. Its pages list this strength: The tool offers a one-click install and run script, Though Python and Git must be installed separately.
β The AI Tool Bible editorial team
Pros
- β The tool offers a one-click install and run script, though Python and Git must be installed separately.
- β Stable Diffusion Web UI supports 4GB video cards, with reports of functionality on 2GB cards.
- β The interface supports custom scripts and many extensions from the community.
- β Users can load checkpoints in safetensors format.
Facts
- Platforms
- windows, linux
- API available
- Yes (not source-checked)
- Open source
- Yes (license: AGPL-3.0)
- GitHub stars
- 165,305 (checked Nov 13, 2026) (not source-checked)
- Last GitHub push
- Mar 2, 2026 (not source-checked)
- First commit
- Aug 2022 (not source-checked)
- Model used
- Stable Diffusion 1.x / 2.x / SDXL and community fine-tunes (Safetensors checkpoints) (not source-checked)
Where this tool sits
Frequently asked
- Is Stable Diffusion Web UI free to use?
- Yes, the tool is listed as free with no specific pricing details provided in the documentation. It is an open-source web interface implemented using the Gradio library for running Stable Diffusion models.
- What hardware is required to run this tool?
- The software supports 4GB video cards, with reports of it working on 2GB cards. Installation instructions are provided specifically for NVidia GPUs, which are recommended for optimal performance and compatibility.
- Can I train custom models or LoRAs within the interface?
- Yes, the Training tab provides options for hypernetworks and embeddings. LoRAs are explicitly supported as a feature similar to Hypernetworks, allowing users to train and utilize these specific model components.
- Does the tool offer image enhancement or upscaling features?
- The Extras tab includes GFPGAN, a neural network that fixes faces, and RealESRGAN, which is available as a neural network upscaler. These tools help improve the quality and resolution of generated images.
- What advanced generation controls are available?
- Users can utilize X/Y/Z plots for 3-dimensional parameter visualization, apply attention weighting to specific text parts, and use prompt editing to change subjects mid-generation. A negative prompt field is also available.